CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-workflow-designer

Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/agent-workflow-designer/SKILL.md

The canonical home for this skill is agent-workflow-designer in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-organized and concise but weakened by dangling bundle references and high-level implementation guidance. The referenced references/ and scripts/ files do not exist, which undercuts both actionability and progressive disclosure.

Suggestions

Add the missing references/workflow-patterns.md and scripts/workflow_scaffolder.py (or remove the references) so the cited paths resolve to real bundle files.

Concretize the Recommended Workflow by specifying required handoff-contract fields and an example retry/timeout policy instead of leaving them as 'define' / 'add' placeholders.

Turn the implicit validation mentions into an explicit checkpoint (e.g. 'Dry-run → inspect output → fix → re-run') so the workflow has a clear feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and bullet-driven with no over-explanation of concepts Claude already knows; minor redundancy (the Overview restates the description) keeps it just short of fully efficient.

4 / 5

Actionability

Quick Start supplies two concrete scaffolder commands and the Pattern Map gives concrete pattern definitions, but the core implementation guidance (handoff contract fields, retry/timeout specifics) stays high-level and is deferred to a references file — and the scaffolder script it points to does not exist in the bundle.

3 / 5

Workflow Clarity

A clear five-step Recommended Workflow sequence is present, but validation checkpoints are implicit ('output validation gates', 'dry-run before scaling') with no explicit validate→fix→retry feedback loop.

3 / 5

Progressive Disclosure

Section structure is clean and the body signals a one-level-deep reference ('Detailed templates: references/workflow-patterns.md'), but the bundle contains no references/ or scripts/ directories, so both referenced paths (workflow-patterns.md and workflow_scaffolder.py) are dangling and navigation breaks.

3 / 5

Total

13

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that concretely states capabilities and gives explicit 'Use when' trigger guidance tied to natural user phrases. It is comprehensive on completeness with only minor gaps in specificity, trigger synonyms, and distinctiveness.

DimensionReasoningScore

Specificity

Lists several concrete capabilities — pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls — but the single verb 'Design' governs them as objects rather than enumerating distinct actions, leaving minor coverage gaps versus a comprehensive 5.

4 / 5

Completeness

Explicitly answers both what ('Design production-grade multi-agent workflows with clear pattern choice, handoff contracts, failure handling, and cost/context controls') and when ('Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases a user would say appear — 'multi-step agent pipeline', 'single-agent vs multi-agent approaches', 'LLM workflow', 'context bloat', 'unreliable handoffs' — giving good keyword coverage, though a few common synonyms (e.g. 'agentic') are absent.

4 / 5

Distinctiveness Conflict Risk

The multi-agent orchestration niche is clear and triggers are specific to agent pipelines/handoffs, but there is minor overlap risk with closely related coding-architecture or general workflow skills.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
alirezarezvani/claude-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.